llama.cpp
Extend llm_build_ffn() to support _scale tensors
#8103

Merged

Extend llm_build_ffn() to support _scale tensors #8103

ggerganov merged 2 commits into ggml-org:master from Eddie-Wang1120:ffn_change

change llm_build_ffn

a671d56e

Merge branch 'master' into ffn_change

c70787d8

ggerganov approved these changes on 2024-06-25

mofosyne added Review Complexity : Low

slaren approved these changes on 2024-06-25

ggerganov merged 494165f3 into master 1 year ago

Reviewers

slaren

ggerganov

Assignees

No one assigned

Labels

Review Complexity : Low

Milestone

No milestone